Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of affection or positive sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    positive sentiment expressions and appreciation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onnaissance
    -0.42
    modelBuilder
    -0.40
     veřej
    -0.37
    MediaStore
    -0.37
    bewerken
    -0.36
    Vía
    -0.36
     publicidad
    -0.36
    +#+#
    -0.36
    Handlung
    -0.36
     publicité
    -0.35
    POSITIVE LOGITS
     surprises
    0.66
     ब्रेकडाउन
    0.61
    Personensuche
    0.54
    きっと
    0.52
    certainly
    0.52
     appreciate
    0.52
     surpresa
    0.50
     surprising
    0.50
     surprise
    0.49
     EconPapers
    0.48
    Act Density 0.012%

    No Known Activations